Research map / Video / Video segmentation and tracking
Robust Video Stabilization by Optimization in CNN Weight Space
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use optical-flow-based optimization in CNN weight space instead of the compared stabilization methods | Video stabilization · 25 example videos | Metric A (accumulated optical flow) | Helped |
| Use optical-flow-based optimization in CNN weight space instead of the compared stabilization methods | Video stabilization · NUS dataset | Metric A (accumulated optical flow) | Helped |
| Use optical-flow-based optimization in CNN weight space instead of the compared stabilization methods | Video stabilization · 25 example videos | Metric B (cropping ratio) | Helped |
| Use optical-flow-based optimization in CNN weight space instead of the compared stabilization methods | Video stabilization · 25 example videos | Metric C (global distortion) | Mixed |
| Use optical-flow-based optimization in CNN weight space instead of the compared stabilization methods | Video stabilization · 25 example videos | Metric D (frequency-domain stability) | Helped |
| Use optical-flow-based optimization in CNN weight space instead of the compared stabilization methods | Video stabilization · 25 example videos | Metric E (motion smoothness) | Helped |
| Add CNN-based optimization after pre-stabilization | Proposed method · 25 example videos | Metric A (accumulated optical flow) | Helped |
| Add continuity regularization for the warp field (ablation) | Optical-flow-based stabilization · Video stabilization examples | visual artifacts | Helped |
| Increase the window size from 10 to 80 frames (ablation) | Proposed method · Video segments | optimization error | Mixed |
| Use more channels in the CNN (ablation) | Proposed method · Video stabilization examples | regression error | Helped |
| Use a more complex CNN structure (ablation) | Proposed method · Video stabilization examples | regression error | Helped |
| Use the simpler network configurations instead of Config 1 (ablation) | Proposed method · 25 example videos | result quality | Hurt |
Closest papers by meaning
- Learning Video Stabilization Using Optical Flow (CVPR 2020 · similarity 0.92)
- 3D Video Stabilization With Depth Estimation by CNN-Based Optimization (CVPR 2021 · similarity 0.89)
- Harnessing Meta-Learning for Improving Full-Frame Video Stabilization (CVPR 2024 · similarity 0.89)
- Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks (NeurIPS 2025 · similarity 0.87)
- AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers (CVPR 2025 · similarity 0.84)
- Training-free Camera Control for Video Generation (ICLR 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.